- Introduction
The appropriate information for the introduction varies with the kind of report. Most introductions provide the reader with the necessary background to help put the objectives and results in a proper perspective. When necessary, previous related work is described. If the report is on several short experiments, the overall purpose and background of the group of experiments should be described first, followed by the necessary information for each of the experiments. In this case, the introduction should not be a mere collection of material on each, but should be written using connected paragraphs with clear transitions between ideas and information.
The introduction should say why this series of tests is being done, and give any relevant background information. - Background and/or Related Work
In this section you would want to talk about the background and or theory of the experiment you are running, as well as connect it to previous research that has been conducted by others in your field. This section is very important in a real paper because reviewers want to know what else has been done, and how you have incorporated previous results into your own work. It’s also important because most reviewers will be familiar with the research in your area, and if they believe you haven’t adequately done a literature review of other work in your area – they will be very unlikely to accept that it’s new. - Experimental Methodology
In this section you want to discuss how exactly you conducted your experiment. In this class, we’ll often use a simulation framework as well as benchmark (test programs) to test our experiments. Because of this, you may want to discuss the simulation framework you used and the benchmarks in separate subsections.
3.1. Simulation Framework
You can discuss the simulator that you used.
3.2. Simulated Workloads
You can discuss the benchmarks that you used including the input parameters.
3.3. Additional Information about the Experiment
Any additional information about your experiment.
- Results
4.1. Results for Test A
You may have run multiple tests and have multiple results, so you can create subsections that have both tables/graphs with the actual results as well as a discussion of those results.
4.2. Results for Test N
You may have run multiple tests and have multiple results, so you can create subsections that have both tables/graphs with the actual results as well as a discussion of those results.
- Conclusion
Base all conclusions on your actual results. Explain the meaning of the experiment and the implications of your results. Examine the outcome in the light of the stated objectives. Seek to make conclusions in a broader context in the light of the results. - References
In this section you need to include any references you used in the paper. You normally number the references based on their appearence. Please see the example paper for a better understanding of this section.
[1] J. Bobba et al., Performance Pathologies in Hardware Transactional Memory, ISCA, 2007
[2] R. Meyer et al., The Coordinate-Exchange Algorithm for Constructing Exact Optimal Experimental Designs, Technometrics, Vol. 37, No. 1, pp60-69, Feb. 1995
[3] P. Joseph et al., Construction and Use of Linear Regression Models for Processor Performance Analysis, HPCA, 2006
[4] Y. Sakamoto et al., Akaike Information Criterion Statistics, Kluwer Academic Publishers, 1987
Sample Solution